Model comparison
Kimi K2.6 vs Magistral Small
Kimi K2.6 is the stronger model overall, scoring 47.5 to 29.9 on the Noometry Index. Magistral Small costs 2.3× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Mistral AISummary
- They share 7 benchmarks with published results for both. Kimi K2.6 scores higher in 4 categories and Magistral Small in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 39.6 to 6.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 96.1% for Kimi K2.6 and 30% for Magistral Small.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Kimi K2.6 accepts more context: 262K tokens versus 128K.
Side by side
| Kimi K2.6 | Magistral Small | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 47.5 | 29.9 |
| Released | 2026-04-20 | 2025-06-10 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 262K | 40K |
| Input $ / M tokens | $0.95 | $0.50 |
| Output $ / M tokens | $4 | $1.50 |
| Results tracked | 51 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.6: 50.5 (#41), Magistral Small: 37.8 (#172)
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| SciCode | 53.5% | 35.2% |
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1509 | — |
| WeirdML | 55.9% | — |
| LMArena Coding | 1488 | — |
| ALE-Bench | 1,093 | — |
Agentic & Tool Use Not comparable
Kimi K2.6: 21.8 (#128), Magistral Small: —
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| OSWorld 2.0 | 4.6% | — |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |
Reasoning Kimi K2.6 leads
Kimi K2.6: 39.6 (#51), Magistral Small: 6.9 (#345)
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| CritPt | 8% | 0.3% |
| Chess Puzzles | 26% | 3% |
| DTBench | 90.9% | 61.3% |
| Epoch Capabilities Index | 151.03 | 133.19 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 6.3% |
| NYT Connections (extended) | 87.2% | — |
| ARC-AGI-1 | — | 5% |
| EBR-Bench | 2.4% | — |
| LMArena Hard Prompts | 1470 | — |
| Mystery Game Puzzles | 18% | — |
| LMCA | 37.3% | — |
Math Kimi K2.6 leads
Kimi K2.6: 56.8 (#34), Magistral Small: 24.9 (#253)
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 96.1% | 30% |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| MathArena Final-Answer Competitions | 72.9% | — |
| ProofBench | 16% | — |
| LMArena Math | 1475 | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Kimi K2.6 leads
Kimi K2.6: 53.9 (#48), Magistral Small: 30.9 (#215)
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| GPQA Diamond | 90.8% | 56.1% |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |
| LMArena Expert | 1491 | — |
Multimodal Not comparable
Kimi K2.6: 31.8 (#95), Magistral Small: —
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| LMArena Vision | 1282 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Not comparable
Kimi K2.6: 55.1 (#35), Magistral Small: —
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| LMArena Non-English | 1446 | — |
| LMArena Chinese | 1521 | — |
| LMArena French | 1471 | — |
| LMArena German | 1449 | — |
| LMArena Japanese | 1442 | — |
| LMArena Korean | 1428 | — |
| LMArena Russian | 1446 | — |
| LMArena Spanish | 1463 | — |
Instruction Following Not comparable
Kimi K2.6: 76.5 (#40), Magistral Small: —
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1451 | — |
Long Context Not comparable
Kimi K2.6: 44.9 (#50), Magistral Small: —
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1468 | — |
Writing & Preference Not comparable
Kimi K2.6: 68.7 (#25), Magistral Small: —
| Benchmark | Kimi K2.6 | Magistral Small |
|---|---|---|
| LMArena Text | 1455 | — |
| LMArena Creative Writing | 1434 | — |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
| LMArena Multi-Turn | 1453 | — |
Frequently asked questions
Is Kimi K2.6 better than Magistral Small?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 29.9 on the Noometry Index. Magistral Small costs 2.3× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.6 or Magistral Small?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Kimi K2.6 or Magistral Small better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 128K.
How many benchmarks do Kimi K2.6 and Magistral Small share?
7 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Magistral Small has 10.